Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2765 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.4850. Min Act: -0.0000

Data Index: 779034 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1186448 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.4046. Min Act: -0.0000

Data Index: 110017 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2102. Min Act: -0.0000

Data Index: 774468 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3206. Min Act: -0.0000

Data Index: 967278 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1879. Min Act: -0.0000

Data Index: 1137406 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2937. Min Act: -0.0000

Data Index: 383079 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.2490. Min Act: -0.0000

Data Index: 577841 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1581. Min Act: -0.0000

Data Index: 276936 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1704. Min Act: -0.0000

Data Index: 1448381 (Python Code)

Max Activating Token Index: 711

Text #10

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1577922 (Python Code)

Max Activating Token Index: 648

Text #11

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0834. Min Act: -0.0000

Data Index: 1133827 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1605218 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0220. Min Act: -0.0000

Data Index: 454753 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0921. Min Act: -0.0000

Data Index: 548670 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1387719 (Python Code)

Max Activating Token Index: 865

Text #16

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0228. Min Act: -0.0000

Data Index: 417741 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1462861 (Python Code)

Max Activating Token Index: 537

Text #18

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.8441. Min Act: -0.0000

Data Index: 356042 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1258187 (C4 (Web Text))

Max Activating Token Index: 1007